🛒 Agent add-ons
New on the Shelf
Fresh add-ons for your agent, each one checked at the source. 🍪
- SDK OpenAI Agents SDK (Python) 0.24.0 🌶️ ✓ verified
OpenAI's agent framework now exposes MCP annotations on converted tools and supports run-wide formatting of tool exceptions. - MCP server Context7 MCP 4.4.2 🌶️ ✓ verified
Upstash's docs-fetching server now advertises a proper title and icons in the MCP handshake, so it looks less anonymous in your client. - MCP server Figma MCP server (skills 2.2.157) 🌶️🌶️ ✓ verified
Figma's official server lets agents read your designs and, on the remote server, draw right on the canvas.
It can even make placeholder images (it asks first and uses Figma AI credits).
The latest bump added figma-spec and figma-code-workflows skills.Sample: Figma (official YouTube): What is the Figma MCP server? - MCP server Supabase MCP server 0.14.0 🌶️🌶️ ✓ verified
Supabase's server adds health-advisor support and bounded cost lifecycle observations, so your agent can check your database's health, not just query it. - Plugin Pika plugin 0.19.3 🌶️🌶️ ✓ verified
Pika's official plugin lets your agent make and edit images, video, music, sound effects and voice.
Comes with task skills for ads, headshots, camera moves, podcasts and more.
Uses the credits on your Pika account. - MCP server MCP reference servers 1.0 🌶️ ✓ verified
The classics grew up: filesystem, memory, everything and sequential-thinking hit 1.0.0 on npm; fetch, git and time got fresh PyPI builds. - SDK Cloudflare Agents 0.28.0 🌶️🌶️ ✓ verified
Cloudflare's agents SDK adds a persistent browser tool and a web_fetch tool that turns most document formats into markdown. - Skill Anthropic claude-api skill 🌶️ ✓ verified
Claude's cheat sheet for building on Claude learned dynamic workflows, four workflow quickstarts, and that Haiku 5.5 is the current Haiku. - MCP server GitHub MCP Server v2.0.0 🌶️🌶️ ✓ verified
GitHub's official server now ships structured outputs and output schemas, so Code Mode agents get typed results instead of guessing (schemas need MCP 2026-07-28+ clients). - Plugin ElevenLabs plugin 🌶️🌶️ ✓ verified
ElevenLabs' official plugin gives your agent a voice.
Skills for text-to-speech, music, sound effects, dubbing and more, plus their hosted MCP server.
Sign in with your ElevenLabs account; no API key needed for the hosted server.Sample: ElevenLabs: official preview of the premade voice "Roger" - MCP server Playwright MCP v0.0.83 🌶️ ✓ verified
Microsoft's browser-driving server got tidier: browser_find can save matches to a file, and navigate/reload report a page-load dialog instead of timing out. - Plugin Runway plugin (Runway MCP) 🌶️🌶️ ✓ verified
Runway's official plugin plugs your agent into Runway's hosted MCP server.
Ask for images, video, music or speech right in chat.
Sign in with your Runway account (no API key); generations spend your plan's credits.Sample: Runway (official YouTube): Introducing Runway MCP - MCP server MiniMax MCP 🌶️ ✓ verified
MiniMax's official server gives your agent text_to_image and generate_video tools (plus voices).
Latest update: moved to MCP SDK v2 and retired the Music tool.
Needs a MiniMax API key.
Sample: MiniMax (official README) - Skill Anthropic canvas-design skill 🌶️ ✓ verified
A recipe card that teaches Claude to make posters and art as .png or .pdf.
It writes a short design philosophy first, then paints it.
Original designs only: the skill says never copy existing artists. - Skill Anthropic algorithmic-art skill 🌶️ ✓ verified
Teaches Claude to make generative art with p5.js: flow fields, particles, seeded randomness.
Original art only, per the skill. - Skill OpenAI imagegen skill 🌶️ ✓ verified
Codex's built-in recipe card for making and editing images: mockups, sprites, textures, cutouts.
By default it uses Codex's own image tool, so no API key. - Skill OpenAI speech skill 🌶️ ✓ verified
Turns text into voiceover, narration or audio prompts with OpenAI's built-in voices.
One clip or a whole batch.
Needs an OPENAI_API_KEY. - MCP server Luma API MCP 🌶️ ✓ verified
Luma's official server: create images (Photon) and videos (Ray) from your MCP client.
Needs a Luma API key and a quick setup script.
Older pick: last updated April 2025.